Claude Skills by trungdo9

Hreflang and international SEO — validate existing hreflang implementations (self-ref, return tags, x-default, language/region codes) and generate correct HTML/HTTP-header/sitemap implementations for multi-language and multi-region sites. Also audits cultural adaptation, content parity, locale formatting, and machine-translation quality across language versions.

AI image generation for SEO assets — OG/social preview images, blog hero images, product photos, schema images, infographics, favicons, Pinterest pins. Maps each use case to the right aspect ratio, resolution, and domain-mode prompt, then packages the result (alt text hook, filename, WebP, schema, OG tags) for shipping. Powers AI-generated media in the seo-writing pipeline (Stage 4) and the generation half of an [[seo-images]] pass.

Image SEO — resolve in-article image placeholders into real images with keyword-rich alt text, descriptive filenames, WebP compression, and lazy loading. Handles featured images and image sitemaps. Powers the media stage of the seo-writing pipeline (Stage 4).

Local SEO analysis — Google Business Profile (GBP) optimization, NAP consistency across page/schema/citations, review-signal health, citation building, LocalBusiness schema by industry vertical, and multi-location doorway-page risk. Detects business type (brick-and-mortar / service-area / hybrid) and industry vertical to route the checks that apply. Use for "local SEO", "Google Business Profile", "GBP", "map pack", "local pack", "citations", "NAP consistency", "service area", or "multi-locati...

Google Maps / map-pack ranking mechanics — geo-grid rank tracking, GBP profile audit via API, cross-platform review intelligence, competitor radius mapping, and cross-platform NAP verification. Three capability tiers (free / DataForSEO / DataForSEO + Google Maps Platform). Analyzes the business on maps PLATFORMS via APIs — not the website's on-page local signals.

Deep single-page SEO audit — on-page elements (title, meta, headers, links), content-quality signals, technical meta tags, schema detection, image checks, and Core Web Vitals signals inferred from HTML. Use when the user says "analyze this page", "check page SEO", "single URL", "page analysis", or hands over one URL/page for review.

SEO planning — turn a topic cluster + content inventory into a prioritized, ordered writing roadmap. Scores what to write first (intent × reach ÷ effort), front-loads pillars, and produces the "kế hoạch viết bài" (content plan). Feeds the seo-writing pipeline as the backlog.

Programmatic SEO — plan and audit pages generated at scale from structured data sources (CSV/API/DB). Covers template architecture, URL patterns, internal-linking automation, thin-content/quality-at-scale gates (2025-2026 Scaled Content Abuse enforcement), canonical strategy, sitemap integration, and index bloat prevention for large page sets.

Detect, validate, and generate Schema.org structured data (JSON-LD preferred). Covers per-type templates (Article, FAQPage, Product, LocalBusiness, BreadcrumbList, and 15+ more), nested @graph patterns, rich-results eligibility, and the deprecated-type guardrails. Powers Stage 4 of the seo-writing pipeline and the seo-schema agent.

XML sitemap analysis and generation — validate an existing sitemap against Google's real rules (50k/50MB caps, lastmod accuracy, extension subtypes), or generate a new one (with index splitting) for a site being built out. Feeds the technical-SEO audit and the sitemap step of the seo-writing pipeline's publish stage.

Search Experience Optimization — reads the SERP backwards to catch page-type mismatches (a blog post competing against product pages), derives user stories from PAA/ads/related-searches, and scores the page from 4-7 SERP-derived personas (relevance/clarity/trust/action). Produces an SXO Gap Score, kept separate from the SEO Health Score, plus an IST/SOLL wireframe on request.

Technical SEO audit across 9 categories — crawlability, indexability, security, URL structure, mobile/page experience, Core Web Vitals, structured-data detection, JavaScript rendering, and IndexNow. Also covers agent-friendly-page auditing (accessibility tree, agentic browsing). Use for "technical SEO", "crawl issues", "robots.txt", "Core Web Vitals", "site speed", "security headers", or an existing-site inventory before a writing campaign.

End-to-end SEO article production pipeline — from keyword strategy to published post. Standardizes a 6-stage flow (research/strategy → competitor analysis + outline → section-by-section writing → on-page optimization → media → internal-link + publish) into a Claude-native workflow. Ported from an n8n production pipeline. Use to plan, write, optimize, and publish complete SEO articles (single or at scale), incl. WordPress. State tracked via a content pipeline table (Supabase or a local plan fi...

Claude-SEO engine root — the orchestrator behind `/mk:seo audit|keywords|ai|programmatic|schema`. Detects business type (SaaS, local, e-commerce, publisher, agency) from homepage signals, dispatches the 24 sibling seo-* skills/agents in parallel, and synthesizes raw findings into a prioritized action plan via a 10-principle framework. Owns the SEO Health Score, quality gates, and the Critical/High/Medium/Low priority model shared by every audit-side sub-skill.

Signup and registration flow optimization — field reduction, social/SSO auth, single vs multi-step, email verification, error and validation UX, drop-off diagnosis, activation handoff. Use when the user says "signup conversions", "registration friction", "signup form optimization", "free trial signup", "reduce signup dropoff", "account creation flow", "people aren't signing up", "signup abandonment", "nobody completes registration", "too many steps to sign up", or "simplify our signup".

SMS and MMS marketing — opt-in mechanics, TCPA/carrier compliance, flow design (welcome, abandoned cart, post-purchase, win-back, replenishment), segment/character budgeting, cadence and frequency caps, platform selection, and revenue-per-send measurement. Use for "SMS marketing", "text message campaign", "SMS sequence", "abandoned cart text", "SMS compliance", "A2P 10DLC", "TCPA", "short code vs toll-free", "MMS campaign", "Klaviyo SMS", "Postscript", "Attentive", "Twilio", or "SMS vs email"...

Write and optimize platform-native social posts — LinkedIn posts and document carousels, X threads, Instagram carousels and Reels, TikTok and Shorts scripts, hooks, hashtags, and character limits. Use for "LinkedIn post", "Twitter thread", "tweet ideas", "carousel", "slide-by-slide", "Reel", "Shorts", "TikTok video", "video hook", "short-form video script", "repurpose this article/podcast/webinar into social", "what should I post", "social listening", "brand mentions", "top posts to comment o...

Post-signup activation and first-run experience — aha moment definition, minimum path to value, onboarding checklists, empty states, guided tours, drop-off diagnosis, stalled-user recovery. Use when the user says "onboarding flow", "activation rate", "user activation", "first-run experience", "empty states", "onboarding checklist", "aha moment", "new user experience", "time to value", "users aren't activating", "nobody completes setup", or "users sign up but don't use the product". For the re...

Token-efficient headless browser automation for AI agents using a snapshot+refs model (~93% less context than traditional tools)

Convert an existing codebase into a CLI + MCP server so AI agents can invoke its functions as tools — picking what to expose, defining schemas, handling auth and side effects.

Generate images via Nano Banana with curated prompts

Create programmatic videos in React, render to MP4

Answer technical and architectural questions about the codebase with researched, in-depth, context-aware responses (not superficial replies). Reads relevant code files, references specific files + line numbers, and explains architectural decisions / patterns found in actual code. Use when user asks "how is X implemented?", "what's the schema for Y?", "explain Z in this project", or any technical / architectural consultation request.

Use when brainstorming software solutions, evaluating architectural approaches, debating technical decisions, or exploring feature ideas before implementation. Acts as a senior architect — challenges assumptions, presents 2-3 viable alternatives with pros/cons, and gives brutally honest feedback under YAGNI/KISS/DRY. Triggers on "/ck:brainstorm", "should we use X or Y", "how should we approach X", "is this worth the complexity", or any high-level architecture/feasibility debate. Does NOT impl...

Puppeteer-based browser automation via single-purpose CLI scripts with persistent sessions and structured JSON output

Build a queryable graph of a codebase from its AST — symbols, imports, call edges, dependency cycles — to support navigation, impact analysis, and refactoring at scale.

Use when the user needs to CREATE, VERIFY, ANALYZE, or REFACTOR a CLAUDE.md file (the project-instructions file Claude Code loads every session). Triggers on "/ck:claude-md", "write CLAUDE.md", "audit CLAUDE.md", "verify CLAUDE.md", "CLAUDE.md too long", "slim down CLAUDE.md", "clean up CLAUDE.md", "which section costs tokens", "CLAUDE.md token cost", "optimize CLAUDE.md". Covers structure standard, token budget, verify checklist (broken refs, phantom commands, duplication, staleness), per-se...

Use when reviewing a branch, a PR, or work-in-progress changes ("review since X"), when receiving code review feedback (especially if unclear or technically questionable), when completing tasks or major features requiring review before proceeding, or before making any completion/success claims. Covers edge-case scouting, pinning the review's fixed point with a merge-base diff, three-axis review (Standards vs Spec vs Security) in parallel subagents reported without reranking, the smell baselin...

Declare or infer a programming experience level (0-5) so explanations, examples, and suggestions adapt — verbose with safety nets at level 1, terse with idioms at level 5.

Design, debug, and optimize AI agent systems when context limits hinder performance — diagnose context degradation, apply Write/Select/Compress/Isolate strategies, and build multi-agent architectures that maximize reasoning quality per token.

Drive a feature from spec to production through hard-gated stages — plan, code, test, docs, deploy — with verification at each gate. Infrastructure-agnostic methodology.

PostgreSQL database guide — SQL queries, JOINs, CTEs, window functions, indexing, EXPLAIN/ANALYZE, user management, backups, replication, psql CLI. Use when writing SQL queries, designing schemas, optimizing performance, or administering PostgreSQL databases. For Supabase-specific RLS, SDK, and Postgres tuning see the `supabase` skill.

Complete Supabase skill — platform layer (Auth, RLS policies, Client SDK JS/Dart/Swift, Storage, Realtime, Edge Functions, CLI migrations) + Postgres SQL layer (query optimization, indexing, connection pooling, schema design, locking, monitoring). Use when integrating Supabase into an app, writing RLS policies, calling supabase-js, handling storage, subscribing to realtime, deploying Edge Functions, or optimizing Postgres queries and schema.

Systematic debugging framework ensuring root cause investigation before fixes. Includes four-phase debugging process, backward call stack tracing, multi-layer validation, and verification protocols. Use when encountering bugs, test failures, unexpected behavior, performance issues, or before claiming work complete. Prevents random fixes, masks over symptoms, and false completion claims.

Hand-drawn style diagrams with Excalidraw

Create flowcharts, diagrams, Gantt, timeline diagrams

Generate AI design via Google Stitch with code export

50+ styles, 161 color palettes, 57 font pairs

Review UI code against Vercel Web Interface Guidelines for accessibility, forms, animation, performance, and interaction compliance

Initialize projects from scratch with modular scaffolds (Next.js, Vite, Svelte, Python, etc.)

Use this agent when building ASP.NET Core web APIs, cloud-native .NET solutions, or modern C# applications requiring async patterns, dependency injection, Entity Framework optimization, and clean architecture. Triggers on: writing/reviewing/refactoring C# code, designing .NET architecture, debugging C# issues, ASP.NET Core, Entity Framework, LINQ, async/await, Blazor, or MAUI development.

Production Next.js 14+ full-stack development — App Router, Server Components, Server Actions, rendering strategies (SSG/SSR/ISR/PPR/Edge), Core Web Vitals > 90, SEO > 95. Use when architecting or implementing complete Next.js applications, optimizing performance, implementing server actions and mutations, or deploying SEO-optimized applications.

Use this skill when building, optimizing, or debugging Node.js backend applications, APIs, CLIs, or microservices. Triggers on: writing/reviewing/refactoring Node.js code, designing async architectures, debugging event loop issues, Express/Fastify/NestJS development, stream processing, worker threads, performance profiling, or Node.js security hardening.

Comprehensive Python development skills covering FastAPI, Django, Flask, data/ML integration, and best practices. Use when building Python backends, APIs, data pipelines, or ML applications.

Use this skill when building, optimizing, or debugging Python 3.11+ applications. Triggers on: writing/reviewing/refactoring Python code, FastAPI/Django/Flask development, async/await patterns, SQLAlchemy ORM, Pydantic validation, pytest-driven development, type-hint coverage with mypy, data science (pandas/NumPy/scikit-learn), performance profiling, or Python security hardening.

Senior React 18+ specialist. Use when optimizing React applications for performance, implementing advanced React 18+ features, or solving complex state management and architectural challenges within React codebases.

All testing layers — Vitest unit, Playwright E2E deep-dive (configs, page objects, debugging, traces), Cucumber BDD, mobile (Appium/Detox), API (Supertest/Newman), k6 load, CI/CD integration, credential management. Use when writing or fixing tests, setting up test infrastructure, chasing a flaky test, or establishing performance baselines. One skill for every layer — there is no second testing toolkit to consult.

Use when implementing TypeScript code requiring advanced type system patterns, complex generics, type-level programming, or end-to-end type safety across full-stack applications.

Controllable re-creation of Claude Code's dynamic-workflow model on ClauKit's own primitives — markdown recipes + Agent-tool fan-out/pipeline over the 30 existing agents, with 4-axis inheritance and hard gates. Use when a task needs deterministic large-ish fan-out + verification (whole-repo audit, N-file migration, cross-checked review, multi-angle plan) under explicit control, NOT the native closed runtime.

Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.